import numpy as np
import pandas as pd
        

import matplotlib.pyplot as plt
from matplotlib.ticker import MaxNLocator
import seaborn as sns
plt.style.use('ggplot')
import dalex as dx

from scipy import stats
from scipy.stats import norm


from sklearn.preprocessing import LabelEncoder 
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer 

import math
import warnings
warnings.filterwarnings('ignore')
np.random.seed(23)

full_df = pd.read_csv('BankChurners.csv')

updated_df = pd.DataFrame()

def tobinary():
    
    # full_df['Attrition_Flag'] = full_df.Attrition_Flag // same thing
    updated_df['Attrition'] = full_df.Attrition_Flag.map({'Existing Customer':1, 'Attrited Customer':0})
    
    updated_df['Gender'] = full_df.Gender.map({'M':1, 'F':0})

numeric_columns = ['Customer_Age','Credit_Limit','Months_on_book','Avg_Utilization_Ratio','Total_Trans_Amt','Dependent_count',
                  'Total_Relationship_Count','Months_Inactive_12_mon','Contacts_Count_12_mon','Total_Revolving_Bal',
                  'Total_Amt_Chng_Q4_Q1','Total_Ct_Chng_Q4_Q1']

def stringtoint():
    missing_income = full_df['Income_Category'].replace({'Unknown': 1 , 'Less than $40K':0, '$40K - $60K':0, 
                                                      '$80K - $120K':0, '$60K - $80K':0, '$120K +':0})
    #missinng data will be replaced with mode:
    income_data    = full_df['Income_Category'].replace({'Unknown': 1 , 'Less than $40K':1, '$40K - $60K':2, 
                                                      '$80K - $120K':4, '$60K - $80K':3, '$120K +':5})
    
    
    
    missing_education = full_df['Education_Level'].replace({'Unknown': 1, 'High School':0, 'Graduate':0, 'Uneducated':0,
                                                         'College':0,'Post-Graduate':0,'Doctorate':0})
    #missinng data will be replaced with mode:
    education_data    = full_df['Education_Level'].replace({'Unknown': 4, 'High School':2, 'Graduate':4, 'Uneducated':1,
                                                         'College':3,'Post-Graduate':5,'Doctorate':6})
    
    updated_df['Missing_Income']    = missing_income
    updated_df['Income_Category']   = income_data
    updated_df['Missing_Education'] = missing_education
    updated_df['Education_Level']   = education_data

def encode():
    global updated_df
    card_dummies = pd.get_dummies(full_df['Card_Category'], prefix='Card')
    marital_dummies = pd.get_dummies(full_df['Marital_Status'], prefix='Marital')
    updated_df = pd.concat([updated_df, marital_dummies, card_dummies], axis=1)

def concat_with_numerics():
    global updated_df
    updated_df = pd.concat([updated_df, full_df.loc[:, numeric_columns]], axis=1)

tobinary()
stringtoint()
encode()
concat_with_numerics()

from sklearn.linear_model import LogisticRegression

m_logreg = LogisticRegression()

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(updated_df.drop('Attrition', axis = 1), updated_df.Attrition, test_size=0.2)

m_logreg = m_logreg.fit(X_train, y_train)